Use PinchTab when an agent needs repeatable browser automation with stable element references, persistent profiles, and low-token page inspection. It fits tasks where a normal browser library is too noisy, brittle, or expensive in context.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Drive Chrome with stable accessibility refs for repeatable browser automation"
slug: "drive-chrome-with-stable-accessibility-refs-for-repeatable-browser-automation"
description: "Use PinchTab when an agent needs repeatable browser automation with stable element references, persistent profiles, and low-token page inspection. It fits tasks where a normal browser library is too noisy, brittle, or expensive in context."
verification: "security_reviewed"
source: "https://github.com/pinchtab/pinchtab/tree/main/skills/pinchtab"
author: "pinchtab"
publisher_type: "Organization"
category: "Browser Automation"
framework: "Multi-Framework"
---
# Drive Chrome with stable accessibility refs for repeatable browser automation
Use PinchTab when an agent needs repeatable browser automation with stable element references, persistent profiles, and low-token page inspection. It fits tasks where a normal browser library is too noisy, brittle, or expensive in context.
## Prerequisites
pinchtab, Chrome/Chromium
## Installation
Use the upstream install or setup path that matches your environment:
- brew install pinchtab/tap/pinchtab
- npm install -g pinchtab
- docker run -d \
Requirements and caveats from upstream:
- **Docker:**
Basic usage or getting-started notes:
- **macOS / Linux:**
- bash
- **Homebrew (macOS / Linux):**
- Source: https://github.com/pinchtab/pinchtab/tree/main/skills/pinchtab
- Extracted from upstream docs: https://raw.githubusercontent.com/pinchtab/pinchtab/HEAD/README.md
## Documentation
- https://github.com/pinchtab/pinchtab
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/drive-chrome-with-stable-accessibility-refs-for-repeatable-browser-automation/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.